How to GAN Event Subtraction

TL;DR

This paper introduces a GAN-based method for efficient event sample subtraction in LHC simulations, outperforming traditional techniques by generating unweighted events with desired phase space distributions.

Contribution

It presents a novel GAN approach for event subtraction that improves efficiency and accuracy over standard methods in high-energy physics simulations.

Findings

GAN can generate unweighted event samples matching target distributions

Method outperforms traditional subtraction techniques in efficiency

Applicable to background subtraction and non-local event inclusion

Abstract

Subtracting event samples is a common task in LHC simulation and analysis, and standard solutions tend to be inefficient. We employ generative adversarial networks to produce new event samples with a phase space distribution corresponding to added or subtracted input samples. We first illustrate for a toy example how such a network beats the statistical limitations of the training data. We then show how such a network can be used to subtract background events or to include non-local collinear subtraction events at the level of unweighted 4-vector events.